ELECTRICA: ELEctronic knowledge base for Clinical care, Teaching and Research In Child Abuse

Current and emerging artificial intelligence applications for pediatric musculoskeletal radiology

Artificial intelligence (AI) is playing an ever-increasing role in radiology (more so in the adult world than in pediatrics), to the extent that there are unfounded fears it will completely take over the role of the radiologist. In relation to musculoskeletal applications of AI in pediatric radiology, we are far from the time when AI will replace radiologists; even for the commonest application (bone age assessment), AI is more often employed in an AI-assist mode rather than an AI-replace or AI-extend mode. AI for bone age assessment has been in clinical use for more than a decade and is the area in which most research has been conducted. Most other potential indications in children (such as appendicular and vertebral fracture detection) remain largely in the research domain. This article reviews the areas in which AI is most prominent in relation to the pediatric musculoskeletal system, briefly summarizing the current literature and highlighting areas for future research. Pediatric radiologists are encouraged to participate as members of the research teams conducting pediatric radiology artificial intelligence research.

High-resolution CT with histopathological correlates of the classic metaphyseal lesion of infant abuse

BACKGROUND

The classic metaphyseal lesion (CML) is a common high specificity indicator of infant abuse and its imaging features have been correlated histopathologically in infant fatalities.

OBJECTIVE

High-resolution CT imaging and histologic correlates were employed to (1) characterize the normal infant anatomy surrounding the chondro-osseous junction, and (2) confirm the 3-D model of the CML previously inferred from planar radiography and histopathology.

MATERIALS AND METHODS

Long bone specimens from 5 fatally abused infants, whose skeletal survey showed definite or suspected CMLs, were studied postmortem. After skeletal survey, selected specimens were resected and imaged with high-resolution digital radiography. They were then scanned with micro-CT (isotropic resolution of 45 μm(3)) or with high-resolution flat-panel CT (isotropic resolutions of 200 μm(3)). Visualization of the bony structures was carried out using image enhancement, segmentation and isosurface extraction, together with volume rendering and multiplanar reformatting. These findings were then correlated with histopathology.

RESULTS

Study of normal infant bone clarifies the 3-D morphology of the subperiosteal bone collar (SPBC) and the radiographic zone of provisional calcification (ZPC). Studies on specimens with CML confirm that this lesion is a fracture extending in a planar fashion through the metaphysis, separating a mineralized fragment. This disk-like mineralized fragment has two components: (1) a thick peripheral component encompassing the SPBC; and (2) a thin central component comprised predominantly of the radiologic ZPC. By manipulating the 3-D model, the varying appearances of the CML are displayed.

CONCLUSION

High-resolution CT coupled with histopathology provides elucidation of the morphology of the CML, a strong indicator of infant abuse. This new information may prove useful in assessing the biomechanical factors that produce this strong indicator of abusive assaults in infants.